Professional Documents
Culture Documents
www.kspjournals.org
March 2016
Volume 3
Issue 1
1. Introduction
2. Literature Review
Several studies address the importance of exports and imports on economic
growth. The findings of these studies indicate that exports and imports have a
statistically significant positive impact on economic growth. We can summarize
some of these studies that have addressed the issue of effect exports and imports on
economic growth as follows:
Afaf, (2015) investigated the impact of exports and imports on the economic
growth of Tunisia over the period1977-2012. The study used Granger Causality
and Johansen Cointegration approach for long run relationship using Augmented
Dickey-Fuller (ADF) and Phillip-Perron (PP) stationarity test, the variable proved
to be integrated of the order one (1) at first difference. Johansen and Juselius
Cointegration test was used to determine the presence or otherwise of a
cointegrating vector in the variables. The study found finding is clarified that
export, import and GDP are found of order one (t) stationary at the first differences.
Therefore, the variables were found to be integrated of order one. The cointegration
test confirmed that GDP, export and import are cointegrated, indicating an
existence of long run equilibrium relationship between all the variables.
Abugamea, (2015)Examined the both the long run and short run relationships
between economic growth, exports and imports of Palestine for the time period
1968-2012, The study used the cointegration and Granger causality tests. The study
found results based on vector error correction models (VECM) confirm the
existence of a long run relation between imports and economic growth and show
that both exports and imports are the main determinants of economic growth in the
Palestinian case. Causality tests confirm VECM results that imports cause changes
in economic growth in the long run but not in the short run. Kalaitzi (2013)
examined the relationship between exports and economic growth in the United
Arab Emirates over the period 1980-2010. The study applied the two-step EngleGranger cointegration test and the Johansen cointegration technique in order to
confirm or not the existence of a long-run relationship between the variables.
Moreover, this study applied a Vector Autoregression Model in order to construct
the Impulse Response Function and the Granger causality test to examine the
causality between exports and economic growth. The findings ofthis study
confirmed the existence of a long-run relationship between manufactured exports,
primary exports and economic growth. In addition, the Granger causality test
JEB, 3(1), B.S.S. Hamdan. p.100-107.
101
4. Method
The study used the panel data method, through the use of three models is: Poold
regression model (PRM), fixed effect model (FEM) and random effect model
(REM). To know any better models to be used in the analysis will be applied tow
test: the first test (test LM) Lagrange multiplier proposal from Preusch and Pagan
in (1980). This test is used to choose between (PRM), (FEM) or (REM), the second
test, Housman test (1978), for choose between (FEM), (REM).
JEB, 3(1), B.S.S. Hamdan. p.100-107.
102
(1)
t-Statistic
-2.141457
3.819033
3.623696
-0.402577
5.407926
Prob.
0.0330
0.0002
0.0003
0.6875
0.0000
As shown table (1) the independent variable (export, import and gross capital
formation) was significant at level of 1%, the labour was in significant at level of
1%. The exports and labour had negative effect, on economic growth in the Arab
countries, import and gross capital formation was positive effect on the economic
growth in the Arab countries. Also the R-Square reached 0.637 in the pooled effect
model.
(2)
Where it is usually assumed that all are independent of all , we can write
this in the usual regression framework by including a dummy variable for each unit
in the model (Hsiao, 2003:p.96). That is,
yit =
N
j=1 j dij
+ xit + it
(3)
t-Statistic
7.282905
4.803968
3.602402
5.981660
17.85217
Prob.
0.0000
0.0000
0.0004
0.0000
0.0000
NT
T1
2
N
T
i=1 t =1 it
N
T
i=1 t =1 it
~x 2
(4)
If the value of (p- value) statistical test (LM),is statistically significant for this
test, it means that FEM, REM, would be better than PRM. It this value is not
statistically significant for the same test, this means that PRM will be better than
the FEM, REM.
Table 3.Result LM Test
Effects Test
Cross-section F
Cross-section Chi-square
Statistic
10742.605807
2049.722519
d.f.
(16,302)
16
Prob.
0.0000
0.0000
As shown table (3) the effects models better than the pooled model.
(5)
Std. Error
0.042116
0.053786
0.034305
0.062245
1.209722
t-Statistic
7.284369
4.790881
3.622762
6.054760
12.62163
S.D.
3.527444
0.150530
Prob.
0.0000
0.0000
0.0003
0.0000
0.0000
Rho
0.9982
0.0018
0.931195
0.930330
Chi-Sq. d.f.
4
Prob.
0.0007
Var(Diff.)
0.000002
0.000002
0.000000
0.000025
Prob.
0.9343
0.5758
0.2164
0.4977
As shown in table (5) the fixed effects models better than the random effects
model.So they study was analysed the results fixed effects models:
= 15.31687 + 0.306909Ex + 0.258478 Im + 0.123597 GCF
+ 0.373511 LO
Copyrights
Copyright for this article is retained by the author(s), with first publication rights granted to
the journal. This is an open-access article distributed under the terms and conditions of the
Creative Commons Attribution license (http://creativecommons.org/licenses/by-nc/4.0).